
    Z j'N                        S SK Jr  S SKJr  S SKrS SKJr  SSKJr  SSK	J
r
Jr  SSKJr  SSKJrJr  SS	KJr  SS
KJr  SSKJrJr  SSKJrJr  SSKJrJr  SSKJr  SSK J!r!J"r"J#r#  SSK$J%r%J&r&  SSK'J(r(  SSK)J*r*   " S S\RV                  5      r,S r-\" S5      S3S j5       r.S\R^                  S\0S\R^                  4S jr1 S4S\RV                  S\R^                  S\R^                  S \R^                  S!\R^                  S-  S"\2S#\2S$\\!   4S% jjr3\" \.5       " S& S'\RV                  5      5       r4 " S( S)\5      r5\" " S* S+\5      5       r6 " S, S-\RV                  5      r7\" " S. S/\65      5       r8\" " S0 S1\6\5      5       r9/ S2Qr:g)5    )Callable)OptionalN   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_func_from_hubuse_kernelized_func)create_causal_mask)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs   )Jais2Configc                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )Jais2MLP,   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  UR                  S9U l        [
        R                  " U R                  U R                  UR                  S9U l	        [        UR                     U l        g )Nbias)super__init__confighidden_sizeintermediate_sizennLinearmlp_biasup_proj	down_projr   
hidden_actact_fnselfr%   	__class__s     y/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/jais2/modeling_jais2.pyr$   Jais2MLP.__init__-   s    !--!'!9!9yy!1!143I3IPVP_P_`4#9#94;K;KRXRaRabV../    c                 `    U R                  U R                  U R                  U5      5      5      $ N)r,   r.   r+   )r0   xs     r2   forwardJais2MLP.forward6   s"    ~~dkk$,,q/:;;r4   )r.   r%   r,   r&   r'   r+   )__name__
__module____qualname____firstlineno__r$   r8   __static_attributes____classcell__r1   s   @r2   r   r   ,   s    0< <r4   r   c                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..N   dim)shapetorchcat)r7   x1x2s      r2   rotate_halfrK   :   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r4   rotary_pos_embc                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXV4$ )aI  Applies Rotary Position Embedding to the query and key tensors.

Args:
    q (`torch.Tensor`): The query tensor.
    k (`torch.Tensor`): The key tensor.
    cos (`torch.Tensor`): The cosine part of the rotary embedding.
    sin (`torch.Tensor`): The sine part of the rotary embedding.
    unsqueeze_dim (`int`, *optional*, defaults to 1):
        The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
        sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
        that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
        k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
        cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
        the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
Returns:
    `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
)	unsqueezerK   )qkcossinunsqueeze_dimq_embedk_embeds          r2   apply_rotary_pos_embrV   A   sS    & --
&C
--
&Cw;q>C/0Gw;q>C/0Gr4   hidden_statesn_repreturnc                     U R                   u  p#pEUS:X  a  U $ U SS2SS2SSS2SS24   R                  X#XU5      n U R                  X#U-  XE5      $ )z
This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
r   N)rF   expandreshape)rW   rX   batchnum_key_value_headsslenhead_dims         r2   	repeat_kvra   [   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr4   modulequerykeyvalueattention_maskscalingdropoutkwargsc                    [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub  X-   n
[
        R                  R                  U
S[        R                  S9R                  UR                  5      n
[
        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )NrC   r   rB   )rE   dtype)ptrainingr   )ra   num_key_value_groupsrG   matmul	transposer(   
functionalsoftmaxfloat32tork   rh   rm   
contiguous)rb   rc   rd   re   rf   rg   rh   ri   
key_statesvalue_statesattn_weightsattn_outputs               r2   eager_attention_forwardrz   g   s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r4   c                     ^  \ rS rSrSrS\S\4U 4S jjr   SS\R                  S\
\R                  \R                  4   S-  S	\R                  S-  S
\S-  S\\   S\
\R                  \R                  4   4S jjrSrU =r$ )Jais2Attention   z=Multi-headed attention from 'Attention Is All You Need' paperr%   	layer_idxc                 P  > [         TU ]  5         Xl        X l        [	        USUR
                  UR                  -  5      U l        UR                  UR                  -  U l	        U R                  S-  U l
        UR                  U l        SU l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR                  U R                  -  UR
                  UR                  S9U l        g )Nr`   g      Tr!   )r#   r$   r%   r~   getattrr&   num_attention_headsr`   r^   rn   rg   attention_dropout	is_causalr(   r)   attention_biasq_projk_projv_projo_projr0   r%   r~   r1   s      r2   r$   Jais2Attention.__init__   sI   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r4   NrW   position_embeddingsrf   past_key_valuesri   rY   c                    UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
Uu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                  [        5      nU" U UU	U
U4U R                  (       d  SOU R                   U R"                  S.UD6u  pUR$                  " / UQSP76 R'                  5       nU R)                  U5      nX4$ )NrB   r   rC           )rh   rg   )rF   r`   r   viewrp   r   r   rV   updater~   r   get_interfacer%   _attn_implementationrz   rm   r   rg   r\   ru   r   )r0   rW   r   rf   r   ri   input_shapehidden_shapequery_statesrv   rw   rQ   rR   attention_interfacery   rx   s                   r2   r8   Jais2Attention.forward   s~    $))#2.88b8$--8{{=166|DNNqRST[[/44\BLLQPQR
{{=166|DNNqRST&#7RU#[ &'6'='=jX\XfXf'g$J(?(M(MKK,,.E)
 %8	%
  $}}C$2H2HLL	%
 	%
! "));;;;FFHkk+.((r4   )r   r%   r`   r   r   r~   rn   r   r   rg   r   NNN)r:   r;   r<   r=   __doc__r   intr$   rG   Tensortupler   r   r   r8   r>   r?   r@   s   @r2   r|   r|      s    G
{ 
s 
4 IM.2(,&)||&) #5<<#=>E&) t+	&)
 &) +,&) 
u||U\\)	*&) &)r4   r|   c                     ^  \ rS rSrS\S\4U 4S jjr     SS\R                  S\R                  S-  S\R                  S-  S	\
S-  S
\S-  S\\R                  \R                  4   S-  S\\   S\R                  4S jjrSrU =r$ )Jais2DecoderLayer   r%   r~   c                 8  > [         TU ]  5         UR                  U l        [        XS9U l        [        U5      U l        [        R                  " UR                  UR                  S9U l
        [        R                  " UR                  UR                  S9U l        g )N)r%   r~   eps)r#   r$   r&   r|   	self_attnr   mlpr(   	LayerNormlayer_norm_epsinput_layernormpost_attention_layernormr   s      r2   r$   Jais2DecoderLayer.__init__   sr    !--'vKF#!||F,>,>FDYDYZ(*V5G5GVMbMb(c%r4   NrW   rf   position_idsr   	use_cacher   ri   rY   c           
          UnU R                  U5      nU R                  " SUUUUUUS.UD6u  pX-   nUnU R                  U5      nU R                  U5      nX-   nU$ )N)rW   rf   r   r   r   r    )r   r   r   r   )
r0   rW   rf   r   r   r   r   ri   residual_s
             r2   r8   Jais2DecoderLayer.forward   s     !,,];>> 
')%+ 3
 
 !0 !55mD/ 0r4   )r&   r   r   r   r   )NNNFN)r:   r;   r<   r=   r   r   r$   rG   r   
LongTensorr   boolr   r   r   r8   r>   r?   r@   s   @r2   r   r      s    d{ ds d /304(,!&HL|| t+ &&-	
  $; #5<<#=>E +, 
 r4   r   c                   R    \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rSrg	)
Jais2PreTrainedModel   r%   modelTr   r   )rW   
attentionsr   N)r:   r;   r<   r=   r   __annotations__base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r|   _can_record_outputsr>   r   r4   r2   r   r      sQ    &*#,-#4"5N!"&*$r4   r   c                      ^  \ rS rSr% \R
                  \S'   SS\4U 4S jjjr\	   SS\S-  S\
S   S\S-  S	\S
\4   4S jj5       r\R                  " 5       \S 5       5       rSrU =r$ )Jais2RotaryEmbeddingi  inv_freqNr%   c                   > [         TU ]  5         UR                  U l        UR                  U l        Xl        U R
                  R                  S   U l        U R                  nU R                  S:w  a  [        U R                     nU" U R
                  U5      u  o@l
        U R                  SUSS9  U R                  SUR                  5       SS9  g )N	rope_typedefaultr   F)
persistentoriginal_inv_freq)r#   r$   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr%   rope_parametersr   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r0   r%   devicerope_init_fnr   r1   s        r2   r$   Jais2RotaryEmbedding.__init__  s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr4   r   ztorch.deviceseq_lenrY   ztorch.Tensorc           	         U R                   S   n[        U SS5      =(       d    U R                  U R                  -  nSnSU[        R
                  " SUS[        R                  S9R                  U[        R                  S9U-  -  -  nXe4$ )	aH  
Computes the inverse frequencies according to the original RoPE implementation
Args:
    config ([`~transformers.PreTrainedConfig`]):
        The model configuration.
    device (`torch.device`):
        The device to use for initialization of the inverse frequencies.
    seq_len (`int`, *optional*):
        The current sequence length. Unused for this type of RoPE.
Returns:
    Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
    post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).

rope_thetar`   Ng      ?r   rC   rk   )r   rk   )	r   r   r&   r   rG   arangeint64rt   float)r%   r   r   baserE   attention_factorr   s          r2   r   4Jais2RotaryEmbedding.compute_default_rope_parameters  s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r4   c                 L   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   rB   r   mpscpuF)device_typeenabledrC   rD   r   )r   r   r[   rF   rt   r   
isinstancetypestrr   rp   rG   rH   rQ   r   rR   rk   )
r0   r7   r   inv_freq_expandedposition_ids_expandedr   freqsembrQ   rR   s
             r2   r8   Jais2RotaryEmbedding.forward3  sN    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E'E!((--[`J`ahhmmfkUC&,,.1F1L1L1NNYYZ[]^_E))UN3C'')d444C'')d444C	 D vvAGGv$cff177f&;;; DCs   BF
F#)r   r%   r   r   r   r6   r   )r:   r;   r<   r=   rG   r   r   r   r$   staticmethodr   r   r   r   r   no_gradr   r8   r>   r?   r@   s   @r2   r   r     s    llV{ V V  %)+/"*d"*(* t* 
~u$	%	* *: ]]_<  <r4   r   c                     ^  \ rS rSrS\4U 4S jjr\\\      SS\	R                  S-  S\	R                  S-  S\	R                  S-  S\S-  S	\	R                  S-  S
\S-  S\\   S\4S jj5       5       5       rSrU =r$ )
Jais2ModeliC  r%   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [
        R                  " UR                  UR                  S9U l        [#        US9U l        SU l        U R)                  5         g s  snf )Nr   r%   F)r#   r$   pad_token_idpadding_idx
vocab_sizer(   	Embeddingr&   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normr   
rotary_embgradient_checkpointing	post_initr   s      r2   r$   Jais2Model.__init__E  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcCbiv1Cbc
 LL!3!39N9NO	.f=&+# 	 ds   D
N	input_idsrf   r   r   inputs_embedsr   ri   rY   c           
      >   US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcU  Ub  UR	                  5       OSn[
        R                  " UR                  S   UR                  S9U-   nUR                  S5      n[        U R                  UUUUS9n	Un
U R                  XS9nU R                  S U R                  R                    H  nU" U
4U	UUUUS.UD6n
M     U R                  U
5      n
[        U
US	9$ )
Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )r   )r%   r  rf   r   r   )r   )rf   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r   r%   get_seq_lengthrG   r   rF   r   rN   r   r   r   r   r   r   )r0   r  rf   r   r   r  r   ri   past_seen_tokenscausal_maskrW   r   decoder_layers                r2   r8   Jais2Model.forwardU  sF    -t";<YZZ *.*;*;I*FM0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L(;;')+%
 &"oomoW![[)H4;;+H+HIM)*$7) /# M J 		-0&++
 	
r4   )r   r   r   r   r   r   r   )NNNNNN)r:   r;   r<   r=   r   r$   r   r   r   rG   r   r   r   FloatTensorr   r   r   r   r8   r>   r?   r@   s   @r2   r   r   C  s    {     .2.204(,26!%2
##d*2
 t+2
 &&-	2

 2
 ((4/2
 $;2
 +,2
 
!2
    2
r4   r   c                   P  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	        SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )Jais2ForCausalLMi  zlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputrW   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g )NFr!   )
r#   r$   r   r   r   r(   r)   r&   r  r   r/   s     r2   r$   Jais2ForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r4   Nr  rf   r   r   r  labelsr   logits_to_keepri   rY   c	           
      |   U R                   " SUUUUUUS.U	D6n
U
R                  n[        U[        5      (       a  [	        U* S5      OUnU R                  USS2USS24   5      nSnUb)  U R                  " SXU R                  R                  S.U	D6n[        UUU
R                  U
R                  U
R                  S9$ )as  
Example:

```python
>>> from transformers import AutoTokenizer, Jais2ForCausalLM

>>> model = Jais2ForCausalLM.from_pretrained("inceptionai/Jais-2-8B-Chat")
>>> tokenizer = AutoTokenizer.from_pretrained("inceptionai/Jais-2-8B-Chat")

>>> prompt = "Hey, are you conscious? Can you talk to me?"
>>> inputs = tokenizer(prompt, return_tensors="pt")

>>> # Generate
>>> generate_ids = model.generate(inputs.input_ids, max_length=30)
>>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
"Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
```)r  rf   r   r   r  r   N)r  r  r   )lossr  r   rW   r   r   )r   r  r   r   slicer  loss_functionr%   r   r   r   rW   r   )r0   r  rf   r   r   r  r  r   r  ri   outputsrW   slice_indicesr  r  s                  r2   r8   Jais2ForCausalLM.forward  s    > ,0:: ,
)%+',
 ,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r4   )r  r   r   )NNNNNNNr   )r:   r;   r<   r=   _tied_weights_keys_tp_plan_pp_planr$   r   r   rG   r   r   r   r  r   r   r   r   r   r8   r>   r?   r@   s   @r2   r  r    s   *,GH23H_-z:;H  .2.204(,26*.!%-.6
##d*6
 t+6
 &&-	6

 6
 ((4/6
   4'6
 $;6
 ell*6
 +,6
 
 6
  6
r4   r  )r   r  r   )r   )r   );collections.abcr   typingr   rG   torch.nnr(   activationsr   cache_utilsr   r   
generationr	   integrationsr
   r   masking_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   utils.output_capturingr   configuration_jais2r   Moduler   rK   rV   r   r   ra   r   rz   r|   r   r   r   r   r  __all__r   r4   r2   <module>r2     s  , %    ! . ) I / 9 O K F & I I G 5 ,<ryy <( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2 )*@)RYY @) +@)F(2 (V ?  $><299 ><B F
% F
 F
R F
+_ F
 F
R Er4   